Units:

12

Description:

The objective of this special topic course is to introduce students to algorithmic and theoretical aspects of sparsity, and more generally, low-dimensional structures, in large-scale data science and machine learning applications. Students will develop expertise at the intersection of optimization, signal processing, statistics and computer science to address emerging challenges of data science. There will be a final project based on the discussed topics.

The course will introduce a mathematical theory for sparse representation, and will cover several fundamental inference problems that are built upon low-dimensional modeling, including compressed sensing, matrix completion, robust principal component analysis, dictionary learning, super resolution, phase retrieval, etc. We will focus on designing optimization-based algorithms that are effective in both theory and practice.

Prerequisites: Probability, linear algebra

Last Modified: 2018-01-23 5:05PM

Semesters offered:

• Spring 2018